CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

council

Trigger this if the user says 'council'.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tstack/skills/council/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean procedural skill: concrete, environment-aware instructions with explicit feedback loops, failure fallbacks, an exact output template, and scope-control guidance, all in about fifty lines with no padding. The only improvement is structural — adding a few section headers would make the phases easier to navigate.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and dense with instructions ('Use one strong model from each of three different providers, at high reasoning effort'), assumes Claude's competence, and never explains concepts Claude already knows. The only near-redundancy (the closing scope-creep lines) is deliberate emphasis, so it fits 'every token earns its place'.

5 / 5

Actionability

Guidance is fully concrete for an instruction-only skill: named tools (`orchestrator_capabilities`, `delegate_task`), example model picks, a copy-paste-ready output table, and edge-case rules like 'If a delegate gives no score, write `no score`. Do not invent one.' — specific examples cover the common cases.

5 / 5

Workflow Clarity

The sequence is explicit (pre-audit fixes → spawn delegates → collect and summarize → score table → PR description placement → fresh review after fixes) with an explicit feedback loop ('Continue this process until all delegates are satisfied') and failure handling ('If you cannot reach three providers... report it instead of substituting'). No destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

A standalone single-purpose skill under ~50 lines with no bundle files and no nested references, so it qualifies for the simple-skill exception — but it is a stream of paragraphs with no section headers to navigate the phases (setup, delegation, scoring, reporting, iteration), which is a minor organization gap rather than 'well-organized sections'.

4 / 5

Total

19

/

20

Passed

Description

35%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description functions only as a trigger clause: it says when to fire but nothing about what the skill does (convening a multi-provider delegate panel for review/feedback). A user or model scanning descriptions cannot tell this skill's capabilities from it. The distinctive keyword keeps conflict risk low, but specificity and completeness are near the bottom of the scale.

Suggestions

State the capability in third person, e.g., 'Convenes a council of three delegate models from different providers to review work, score it out of 10, and summarize findings and recommendations.'

Use standard 'Use when...' phrasing and broaden trigger coverage beyond the single word 'council' (e.g., 'Use when the user says 'council' or asks for a panel/delegate review of their work').

Mention the core outcomes (review scores, PR-description results table, iterate-until-satisfied loop) so the description distinguishes this from generic code-review skills.

DimensionReasoningScore

Specificity

The description 'Trigger this if the user says 'council'' names no concrete actions or domain at all — it is pure trigger guidance with no capability statement, matching the 'entirely vague; no concrete actions' anchor.

1 / 5

Completeness

Only the 'when' is present ('Trigger this if the user says 'council'') with no statement of what the skill does — exactly the anchor-2 case 'only 'when' is present without 'what'. The explicit trigger means the missing-'Use when' cap of 3 is not the binding constraint; it is genuinely a 2.

2 / 5

Trigger Term Quality

The single keyword 'council' is natural and exactly what a user would say to invoke this skill, but there are no variations or synonyms (e.g., 'panel', 'delegate review'), matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The distinctive single-word trigger 'council' gives a clear niche with minor overlap risk (the word can occasionally appear in unrelated contexts like 'city council'), but the description offers no capability context to further distinguish it — mostly distinct with minor overlap.

4 / 5

Total

10

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

adamsardo/tstack-marketplace

Path

plugins/tstack/skills/council/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.